Background
The World Bank collects statistical information from countries around the world. A particularly useful data set is the World Development Indicators (WDI) which are country level statistical information from around the world.
R is unique in that using library(WDI) you can download indicator data directly from the World Bank, read it into a data set, and put it to use. Using library(plotly) you can even make cool looking motion charts, somewhat reminiscent of those popularized by Hans Rosling.
While the code below is seemingly arcane, it is important to recognize that it is simple in structure. It is very possible to re-purpose the code below using some of the many 1,000’s of WDI indicators that are of interest to you.
Call Relevant Libraries
Get Some Data From the World Development Indicators (WDI)
Show code
# get names of specific indicators from WDI Data Catalog
mydata <- WDI(country="all",
indicator=c("SI.POV.GINI", # Gini
"NY.GDP.PCAP.CD", # GDP
"SE.ADT.LITR.ZS", # adult literacy
"SP.DYN.LE00.IN", # life expectancy
"SP.POP.TOTL", # population
"SN.ITK.DEFC.ZS"), # undernourishment
start = 1980,
end = 2017,
extra = TRUE)
save(mydata, file="WorldBankData.RData")
Rename Some Variables
Show code
# think about renaming some variables with more intuitive names
# e.g....
# rename some variables with dplyr (just copy and paste your indicators)
mydata <- dplyr::rename(mydata,
GDP = NY.GDP.PCAP.CD,
adult_literacy = SE.ADT.LITR.ZS,
life_expectancy = SP.DYN.LE00.IN,
population = SP.POP.TOTL,
Gini = SI.POV.GINI,
undernourishment = SN.ITK.DEFC.ZS)
mydata$country_name <- mydata$country
mydata$country <-as.factor(mydata$country)
save(mydata, file="WorldBankData.RData")
Take a Quick Look at the Data
Show code
# head(mydata) # look at the data
mydata %>%
select(country,
region,
year,
GDP,
adult_literacy,
life_expectancy,
population,
Gini,
undernourishment) %>%
datatable(rownames = FALSE,
filter = 'top',
extensions = 'Buttons',
options = list(
dom = 'Bfrtip',
buttons = c('copy', 'csv', 'excel', 'pdf', 'print')),
caption = 'World Bank Data')
ggplot Graphs
Show code
p1 <- ggplot(mydata,
aes(x = GDP,
y = life_expectancy,
color = region)) +
geom_point() +
geom_smooth() +
scale_color_viridis_d() +
labs(title = "Life Expectancy by GDP",
x = "GDP",
y = "Life Expectancy")
p1
Show code
p1 + facet_wrap(~region)
Map
Show code
Globe
Show code
myglobe <- mydata %>%
filter(year == 2015) %>%
plot_geo(locations = ~iso3c,
color = ~life_expectancy,
z = ~life_expectancy,
text = ~country) %>%
layout(title = "Countries by Life Expectancy in 2015",
geo = list(showland = FALSE,
showcountries = TRUE,
projection = list(type = 'orthographic',
rotation = list(lon = -30,
lat = 10,
roll = 0)))) %>%
colorbar(title = 'life expectancy')
myglobe
Plot the Motion Charts
Show code
mydata <- mydata %>%
filter(region != "Aggregates") # remove aggregates
Life Expectancy by Year
ggplot with ggplotly
Show code
p0 <- ggplot(mydata,
aes(x = year,
y = life_expectancy,
color = region,
size = population,
frame = year)) +
geom_point() +
labs(title = "Life Expectancy by Year",
x = "Year",
y = "Life Expectancy") +
scale_color_discrete(name = "Region")
ggplotly(p0)
plotly
Show code
p1 <- mydata %>%
plot_ly(x = ~year,
y = ~life_expectancy,
color = ~region,
size = ~population,
text = ~country,
hoverinfo = "text")
p1 %>%
# add_markers(color = I("grey"),
# alpha = 0.1,
# name = "All Years",
# type = 'scatter',
# mode = 'lines') %>%
add_markers(frame = ~year,
ids = ~country) %>%
animation_opts(1000,
redraw = FALSE) %>%
layout(title = "Life Expectancy by Year",
yaxis = list(title = "life expectancy"))
Life Expectancy by GDP
Show code
p2 <- mydata %>%
# filter(!is.na(GDP)) %>%
# filter(is.finite(GDP)) %>%
plot_ly(x = ~GDP,
y = ~life_expectancy,
size = ~population,
color = ~region,
frame = ~year,
text = ~country,
hoverinfo = "text",
type = 'scatter',
mode = 'markers',
showlegend = FALSE) %>%
layout(title = "Life Expectancy by GDP",
yaxis = list(title = "life expectancy"))
p2
Life Expectancy by Logged GDP
Using logged GDP on the x axis means that we are looking at relative, instead of absolute changes in GDP.
Show code
p1a <- mydata %>%
ggplot(aes(x = GDP,
y = life_expectancy,
color = region,
frame = year)) +
geom_point() +
labs(title = "Life Expectancy by GDP",
x = "GDP",
y = "life expectancy") +
theme_minimal() +
theme(legend.position="bottom")
ggplotly(p1a)
Show code
base <- mydata %>%
plot_ly(x = ~GDP,
y = ~life_expectancy,
color = ~region,
size = ~population,
text = ~country,
hoverinfo = "text") %>%
layout(xaxis = list(type = "log"))
base %>%
add_markers(color = I("grey"),
alpha = 0.1,
name = "All Years") %>%
add_markers(frame = ~year,
ids = ~country) %>%
animation_opts(1000,
redraw = FALSE)
Show code
p3 <- mydata %>%
# filter(!is.na(GDP)) %>%
# filter(is.finite(GDP)) %>%
plot_ly(x = ~Gini,
y = ~life_expectancy,
size = ~population,
color = ~region,
frame = ~year,
text = ~country,
hoverinfo = "text",
type = 'scatter',
mode = 'markers',
showlegend = FALSE) %>%
layout(title = "Life Expectancy by Gini Coefficient of Inequality",
yaxis = list(title = "life expectancy"))
p3
Three Dimensional Scatterplot
Show code
p2 <- plot_ly(mydata,
x = ~year,
y = ~GDP,
z = ~life_expectancy,
size = ~population,
color = ~region,
text = ~country,
# hoverinfo = "text",
# type = 'scatter',
# mode = 'markers',
theta = 45,
showlegend = FALSE) %>%
layout(title = "Life Expectancy by Year",
yaxis = list(title = "life expectancy"))
p2